import numpy as np
import pandas as pd
import os, gc
from glob import glob
from tqdm import tqdm

from sklearn.preprocessing import MinMaxScaler

from matplotlib import pyplot as plt
import seaborn as sns
sns.set()

import sys
sys.path.append(f'/home/{os.environ.get("USER")}/PythonLibrary')

import EDA

X_train = pd.read_csv('../input/train.csv.zip')
X_train['ind'] = X_train.index

y_train = X_train['target']
X_train = X_train.iloc[:,2:]

X_train_0 = X_train[y_train==0]
X_train_1 = X_train[y_train==1]

X_train_0.var_0.plot(label='target 0', legend=True, alpha=0.9)
X_train_1.var_0.plot(label='target 1', legend=True, alpha=0.9)

<matplotlib.axes._subplots.AxesSubplot at 0x7f7d8c820e10>

M, N = 5, 5
col_list = list( zip(*[iter(X_train_0.columns[:-1])]*(5*5)) )
for col in col_list:
    fig, axes = plt.subplots(ncols=M, nrows=N, figsize=(28, 25), sharex=True)
    for i,(ax, c) in enumerate(zip(axes.ravel(), col)):
        X_train_0[c].plot(ax=ax, title=c, label='target 0', legend=True, alpha=0.9)
        X_train_1[c].plot(ax=ax, label='target 1', legend=True, alpha=0.9)
    plt.show()